multi

agent
Security Audit
Fail
Health Warn
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Fail
  • rm -rf — Recursive force deletion command in evals/run.sh
  • rm -rf — Recursive force deletion command in scripts/providers.sh
  • rm -rf — Recursive force deletion command in scripts/run-dir.sh
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Use [Multi]ple AI agents for code-review, verifying and questions

README.md

multi

[🇷🇺 →] · [🇨🇳 →]

run multiple ai models for one task - code-review, planning, questions - and get multiple opinions.


what's this about?

multi runs one task through several AIs at once — code review, "is it actually done", adhd planning, or just a question — and shows you where the models converge and where they split. you judge, not them.

currently supports:

  • claude subagents
  • codex
  • opencode
  • gemini
  • headless claude code with any API key you provide (e.g. openrouter)

it can use all of those models but it doesn't mean it's gonna be better — they're all still just LLMs. just use whatever you have or you want (or everything at once idc yolo)

commands

  1. /multi:code-review - code-review with multiple agents, then veryfing finds + ponytail lens for overengineering
  2. /multi:check-if-done - the "no bro is it REALLY done" one. a model that just wrote the code
    is the worst judge of whether it works, so this asks models that didn't write it, and refuses
    to call anything done without actually running a command that proves it. should fix "looks done but not really done sorry lmao" cases
  3. /multi:ask - just ask everyone the same thing and see three answers - u'll get three answers, no merging, no judjign
  4. /multi:adhd - summons every model with adhd skill. like mega-cool-planning mode
  5. /multi:setup - tells you what this plugin is about and how to connect everything and etc

install
claude plugin marketplace add szarkans/multi
claude plugin install multi@szkills

or
npx skills add szarkans/multi

or
git clone https://github.com/szarkans/multi ~/.claude/skills/multi

then restart claude code and use /multi:setup

why your README written like that?

Because it was written by me, human. Mostly.
I'm really tired of b2b-ai-saas-skills-loop-code readme's.

evals

TBA.

license
                          __/\\\\____________/\\\\__/\\\\\\\\\\\__/\\\\\\\\\\\\\\\_______        
                           _\/\\\\\\________/\\\\\\_\/////\\\///__\///////\\\/////________       
                            _\/\\\//\\\____/\\\//\\\_____\/\\\___________\/\\\_____________      
                             _\/\\\\///\\\/\\\/_\/\\\_____\/\\\___________\/\\\_____________     
                              _\/\\\__\///\\\/___\/\\\_____\/\\\___________\/\\\_____________    
                               _\/\\\____\///_____\/\\\_____\/\\\___________\/\\\_____________   
                                _\/\\\_____________\/\\\_____\/\\\___________\/\\\_____________  
                                 _\/\\\_____________\/\\\__/\\\\\\\\\\\_______\/\\\________/\\\_ 
                                  _\///______________\///__\///////////________\///________\///__

Reviews (0)

No results found